llama.cpp
`server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3 w/ enable_thinking:false)
#13771

Merged

Commits

server: fix/test add_generation_prompt

ochafik committed 325 days ago
tools: enable hermes2/qwen chat logic even w/o tools

ochafik committed 325 days ago
server: add --reasoning-format=disabled to disable thinking (incl. qwen3 w/ enable_thinking:false)

ochafik committed 325 days ago
Update README.md

ochafik committed 325 days ago
Add models/templates/Qwen-Qwen3-0.6B.jinja

ochafik committed 325 days ago
update --reasoning-format={disabled -> nothink} as suggested

ochafik committed 325 days ago
fix command r7b's nothink w/ official template

ochafik committed 325 days ago
rewrite docs as list as suggested

ochafik committed 325 days ago
Update common/chat.cpp

ochafik committed 325 days ago
Merge branch 'enable-thinking' of github.com:ochafik/llama.cpp into enable-thinking

ochafik committed 325 days ago
const char* return for chat enum name helpers

ochafik committed 325 days ago
switch to --reasoning-budget flag

ochafik committed 324 days ago
Merge branch 'fix-gen-prompt' into enable-thinking

ochafik committed 324 days ago